Senior Applied AI Engineer
$180k - $240k • San Francisco • FullTime
Posted 2mo ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
Applied AI Engineer
About the job
Sauna by Wordware is building a new kind of software that integrates AI with traditional tools, creating a shared intelligence system. We are a well-funded, early-stage startup with a strong backing and a mission to make software more intuitive and powerful. As a Senior Applied AI Engineer, you will be instrumental in building, refining, and scaling our agent systems from the ground up. This senior role requires you to take ownership of these critical systems, ensuring their performance, reliability, and scalability in production environments. You will collaborate across engineering disciplines to ensure our agents function effectively and will have a significant influence on how the team develops them.
Responsibilities
- Build, refine, and scale agent systems, covering architecture, evaluation, and deployment.
- Implement multi-step, tool-using agents that interact with real APIs, handling complexities like retries, authentication, and edge cases.
- Design and implement agent memory systems for persistent state management across runs.
- Develop agents capable of proactive work and sending reminders.
- Own and evolve the agent evaluation framework, including automated checks and human-in-the-loop scoring.
- Investigate and resolve production failures by analyzing traces and fixing underlying systems.
- Proactively identify and address agent problems without explicit task assignments.
- Make architectural decisions with incomplete information and document the reasoning.
- Define and enforce reliability standards for agents, holding releases to these standards.
- Review code and design documents from other team members to improve overall quality.
Requirements
- 4+ years of engineering experience, with a proven track record of shipping production software.
- Experience building and deploying agent-like systems (e.g., multi-step LLM pipelines, tool-using bots).
- Experience running at least one agent system in production, including making architectural decisions and understanding tradeoffs.
- Hands-on experience with agent orchestration and memory management.
- Hands-on experience with tool use and orchestration (e.g., API calls, plugins, auth flows).
- Hands-on experience with evaluation metrics, regression testing, and improving agent behavior.
- Ability to write production-grade code and work across systems independently.
- A preference for shipping functional software over prolonged polishing.
- Experience shipping agents used by customers in production environments.
- Familiarity with LLM operations, tracing, observability, and failure handling.
- Experience as a founder or early engineer, demonstrating a high bar for work quality.
- Experience mentoring or leading other engineers.
Benefits
- Base salary: $180K–$240K
- Meaningful early-stage equity
- Health insurance
- Dental insurance
- 401(k)
- Considerable PTO
- Gym budget
- Lunch